{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OVWIG3DXFAPEY2WZAR3HHXCCD","short_pith_number":"pith:3OVWIG3D","schema_version":"1.0","canonical_sha256":"dbab641b63b940f26356c823b39ee210c1942ba9e4fea9e7026ef03b15081387","source":{"kind":"arxiv","id":"2310.13227","version":1},"attestation_state":"computed","paper":{"title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Ryan A. Rossi, Saayan Mitra, Somdeb Sarkhel, Tong Yu, Victor Bursztyn, Xiang Chen, Yuchen Zhuang","submitted_at":"2023-10-20T02:24:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the action space, amplifying the critical need for efficient action space navigation. However, existing methods either struggle with unidirectional exploration in expansive action spaces, trapped into a local"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.13227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T02:24:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"96400dea6c3e36ec4105b5ce51b115ae34904cdd8d44a1d619959a7a9994bfb6","abstract_canon_sha256":"56ba712e753751f6e7f9eaa4ff690cee48878b87830ddc7febf605e839000124"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:59.547131Z","signature_b64":"RRKaPc9CYvQko2zSAPhq5aDCMX88cFAsglgahy60nRPITq/nhsvH1V80Z2uc3E+AAipKlStcz2twMGv6RL1+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbab641b63b940f26356c823b39ee210c1942ba9e4fea9e7026ef03b15081387","last_reissued_at":"2026-07-05T07:02:59.546554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:59.546554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Ryan A. Rossi, Saayan Mitra, Somdeb Sarkhel, Tong Yu, Victor Bursztyn, Xiang Chen, Yuchen Zhuang","submitted_at":"2023-10-20T02:24:35Z","abstract_excerpt":"Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the action space, amplifying the critical need for efficient action space navigation. However, existing methods either struggle with unidirectional exploration in expansive action spaces, trapped into a local"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13227","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.13227/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.13227","created_at":"2026-07-05T07:02:59.546623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13227v1","created_at":"2026-07-05T07:02:59.546623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13227","created_at":"2026-07-05T07:02:59.546623+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OVWIG3DXFAP","created_at":"2026-07-05T07:02:59.546623+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OVWIG3DXFAPEY2W","created_at":"2026-07-05T07:02:59.546623+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OVWIG3D","created_at":"2026-07-05T07:02:59.546623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21943","citing_title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","ref_index":285,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32025","citing_title":"Generative Skill Composition for LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19500","citing_title":"NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00432","citing_title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12421","citing_title":"Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08491","citing_title":"Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD","json":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD.json","graph_json":"https://pith.science/api/pith-number/3OVWIG3DXFAPEY2WZAR3HHXCCD/graph.json","events_json":"https://pith.science/api/pith-number/3OVWIG3DXFAPEY2WZAR3HHXCCD/events.json","paper":"https://pith.science/paper/3OVWIG3D"},"agent_actions":{"view_html":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD","download_json":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD.json","view_paper":"https://pith.science/paper/3OVWIG3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13227&json=true","fetch_graph":"https://pith.science/api/pith-number/3OVWIG3DXFAPEY2WZAR3HHXCCD/graph.json","fetch_events":"https://pith.science/api/pith-number/3OVWIG3DXFAPEY2WZAR3HHXCCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD/action/storage_attestation","attest_author":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD/action/author_attestation","sign_citation":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD/action/citation_signature","submit_replication":"https://pith.science/pith/3OVWIG3DXFAPEY2WZAR3HHXCCD/action/replication_record"}},"created_at":"2026-07-05T07:02:59.546623+00:00","updated_at":"2026-07-05T07:02:59.546623+00:00"}